Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to personal thoughts and reflections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    REDACTED
    -1.14
    itia
    -1.14
    cknow
    -1.08
    arine
    -1.05
    onda
    -1.00
    VIDIA
    -0.92
    DonaldTrump
    -0.92
     Policies
    -0.89
    rules
    -0.89
    cision
    -0.87
    POSITIVE LOGITS
     irresist
    1.48
    oola
    1.34
    lees
    1.28
     enormously
    1.16
     sorely
    1.14
     dearly
    1.13
     itch
    1.13
     exponentially
    1.11
    ificantly
    1.11
    izont
    1.09
    Act Density 4.712%

    No Known Activations